‘ChatGPT will glaze anyone regardless’: I tried 5 ways to make ChatGPT flatter and agree with me — here’s what happened
1 distinct publishers, one article each in this sample.
Ownership mix: Other: 1
1 publishers · 1 articles · switch to 1-minute for disagreement and framing.
What happened
Is AI less sycophantic now? I tried to make ChatGPT flatter, validate and agree with me and was surprised by what it did next.
Why the coverage differs
AI-assisted comparison · labeled · generated just generated or not yet stored · not a verdict
This story is currently covered by only 1 source. Comparison requires at least two sources from different bias positions.
Comparison summary
AI-assisted · Cerebras / Llama · just generated or not yet stored · inspect sources below rather than trusting this alone
This story is currently covered by only 1 source. Comparison requires at least two sources from different bias positions.
Report timeline
Oldest → newest among clustered members. Gaps may mean delayed pickup, not silence.
-
Sep 12, 2026, 2:00 AM
Coverage by perspective
Perspective labels are external consensus ratings (AllSides / Ad Fontes / MBFC-style), not WeSearch truth scores. Center is not automatically more accurate.
Center · 1
Headline framing
Vocabulary fingerprints · not a political endorsement
No framing analysis for this cluster yet.
Bias/ownership: published methodology on source profiles · AI text always labeled · no reader paywall · no engagement ranking of news · transparency · contribute Ws · home